# An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild

arXiv: https://arxiv.org/abs/1605.04253 · HTML: https://mlsanity.com/paper/1605.04253/

## Key facts

- Cited by 146 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2016.

## Built on by (most cited first, 30 of 146)

- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Does CLIP Bind Concepts? Probing Compositionality in Large Image Models](https://mlsanity.com/paper/2212.10537/) (2022)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Detecting Human-Object Interaction via Fabricated Compositional Learning](https://mlsanity.com/paper/2103.08214/) (2021)
- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [Learning to Compose Soft Prompts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2204.03574/) (2022)
- [A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future](https://mlsanity.com/paper/2307.09220/) (2023)
- [Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2108.06230/) (2021)
- [Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.14475/) (2022)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Independent Prototype Propagation for Zero-Shot Compositionality](https://mlsanity.com/paper/2106.00305/) (2021)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Learning Domain Invariant Prompt for Vision-Language Models](https://mlsanity.com/paper/2212.04196/) (2022)
- [Learning Attention as Disentangler for Compositional Zero-shot Learning](https://mlsanity.com/paper/2303.15111/) (2023)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation](https://mlsanity.com/paper/2306.11087/) (2023)
- [Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language](https://mlsanity.com/paper/2203.03598/) (2022)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [Few-shot Class-incremental Learning for Classification and Object Detection: A Survey](https://mlsanity.com/paper/2308.06764/) (2023)
- [Learning Invariant Visual Representations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.00415/) (2022)

## Abstract (arXiv)

Zero-shot learning (ZSL) methods have been studied in the unrealistic setting where test data are assumed to come from unseen classes only. In this paper, we advocate studying the problem of generalized zero-shot learning (GZSL) where the test data's class memberships are unconstrained. We show empirically that naively using the classifiers constructed by ZSL approaches does not perform well in the generalized setting. Motivated by this, we propose a simple but effective calibration method that can be used to balance two conflicting forces: recognizing data from seen classes versus those from unseen ones. We develop a performance metric to characterize such a trade-off and examine the utility of this metric in evaluating various ZSL approaches. Our analysis further shows that there is a large gap between the performance of existing approaches and an upper bound established via idealized semantic embeddings, suggesting that improving class semantic embeddings is vital to GZSL.